Context models and out-of-context objects
Context models and out-of-context objects
复制标题
DOI：
10.1016/j.patrec.2011.12.004
复制
发表时间：
2012-05-01
影响因子：
5.1
通讯作者：
Willsky, Alan S.
中科院分区：
文献类型：
--
作者：
Choi, Myung Jin;Torralba, Antonio;Willsky, Alan S.
图像的上下文包含有关自然场景和对象如何相互关联的丰富信息。这种背景信息有可能使自然场景和图像的连贯理解。然而，上下文模型的评估主要是基于对象识别性能的提高，即使它只是利用上下文信息的许多方法之一。在本文中，我们提出了一个新的场景理解问题的评估和应用上下文模型。我们感兴趣的是寻找“脱离上下文”的场景和对象。检测“脱离上下文”的对象和场景是具有挑战性的，因为只有在仔细和精确地建模对象之间的关系时才能检测到上下文违规。为了解决这个问题，我们评估上下文信息的不同来源，并提出了一个图形模型，结合这些来源。我们表明，对象之间的物理支持关系可以提供有用的上下文信息，对象识别和上下文检测。(C)2011 Elsevier B.V.保留所有权利。
The context of an image encapsulates rich information about how natural scenes and objects are related to each other. Such contextual information has the potential to enable a coherent understanding of natural scenes and images. However, context models have been evaluated mostly based on the improvement of object recognition performance even though it is only one of many ways to exploit contextual information. In this paper, we present a new scene understanding problem for evaluating and applying context models. We are interested in finding scenes and objects that are "out-of-context". Detecting "out-of-context" objects and scenes is challenging because context violations can be detected only if the relationships between objects are carefully and precisely modeled. To address this problem, we evaluate different sources of context information, and present a graphical model that combines these sources. We show that physical support relationships between objects can provide useful contextual information for both object recognition and out-of-context detection. (C) 2011 Elsevier B.V. All rights reserved.